AutoRLBench 38 Issue / 19 Solution: leaderboard

Metric: Pass rate over 38 issue judgments and 19 solution runs (%). Source: thinking-space.github.io. Saturation forecast: Around April 2028. 9 models tracked. Updated 18 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6 AstraMax33.3#7
2GPT-6.1 SolMax33.3#12
3GLM-5.3Max26.3#72
4Kimi K3.1 ProMax22.8#32
5Claude Fable 5.1Max19.3#17
6Qwen 3.8 MaxMax19.3#63
7Grok 4.7Max17.5#48
8Kimi K3Max7#60
9DeepSeek V4 ProMax3.5#194

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=autorlbench-38-issue-19-solution · How It Works · Data refreshed daily, snapshot 2026-11-18.